RayEmb: Arbitrary Landmark Detection in X-Ray Images Using Ray Embedding Subspace

TL;DR

RayEmb introduces a novel approach for detecting arbitrary landmarks in X-ray images by representing 3D points as subspaces of feature vectors, improving registration accuracy without manual landmark annotation.

Contribution

The paper presents a new method that uses ray embeddings to detect landmarks in X-ray images, eliminating the need for fixed landmark annotation and enhancing registration robustness.

Findings

Outperforms conventional landmark detection methods

Effective in challenging view angles with poor landmark visibility

Validated on synthetic and real X-ray datasets

Abstract

Intra-operative 2D-3D registration of X-ray images with pre-operatively acquired CT scans is a crucial procedure in orthopedic surgeries. Anatomical landmarks pre-annotated in the CT volume can be detected in X-ray images to establish 2D-3D correspondences, which are then utilized for registration. However, registration often fails in certain view angles due to poor landmark visibility. We propose a novel method to address this issue by detecting arbitrary landmark points in X-ray images. Our approach represents 3D points as distinct subspaces, formed by feature vectors (referred to as ray embeddings) corresponding to intersecting rays. Establishing 2D-3D correspondences then becomes a task of finding ray embeddings that are close to a given subspace, essentially performing an intersection test. Unlike conventional methods for landmark estimation, our approach eliminates the need for manually annotating fixed landmarks. We trained our model using the synthetic images generated from CTPelvic1K CLINIC dataset, which contains 103 CT volumes, and evaluated it on the DeepFluoro dataset, comprising real X-ray images. Experimental results demonstrate the superiority of our method over conventional methods. The code is available at https://github.com/Pragyanstha/rayemb.